Al Hotimski

Geospatial Data Scientist at The Conservation Fund. MS in Remote Sensing & Geospatial Sciences.

My work focuses on crafting data systems for complex ownership structures, spatial change over time, climate-related risk. Better data leads to better decisions for the landscapes and communities those decisions affect.

Outside of work I enjoy painting with watercolors, reading, and teaching friends to play pickleball.

Education

Boston University, MS Remote Sensing and Geospatial Sciences (Environmental Data Science), Dean’s List, BA Earth and Environmental Science (Computer Science Minor) (2021-2025)

Coursework: Advanced GIS, Remote Sensing, Data Structures, Python Programming, Statistical Modeling, Environmental Science

Experience

The Conservation Fund, Geospatial Data Scientist (Internship Jun-Dec 2025, Full-time Mar 2026-Present)

  • Built automated USDA NRCS ACEP easement eligibility screening tool; reduced analysis time from 20+ hours to 10 minutes, projecting $12,000/year in savings
  • Designed geodatabase tracking land parcelization, boundary changes, and ownership transfers; built custom fuzzy-matching package to resolve owner name inconsistencies at scale; reduced manual QA by 93%
  • Integrating Salesforce with ArcGIS Online to automate spatial layer sync and replace manual project intake workflows
  • Applied CCDC in Google Earth Engine across ~20,000 acres for historical forest disturbance and carbon accounting

PLACES Lab, Boston University, Research Assistant (May-Aug 2025)

  • QA/QC and accuracy assessment across 800+ georeferenced locations spanning 25 years of land cover change

Volunteer Work

Girls Who Code, Instructor (2020-2021) Taught introductory programming to students from underrepresented communities.

Boston Housing Authority, Volunteer (Ongoing) Contributed to Urban Heat Vulnerability research identifying heat exposure risk at BHA properties.

Family Service of the Lehigh Valley, Volunteer (Ongoing)

Approach

My work emphasizes:

  • Clear problem framing: defining what question the data actually answers
  • Transparency: documenting assumptions and data limitations explicitly
  • Scalability: building systems that can be rerun and extended, not one-off analyses
  • Domain knowledge: treating subject-matter expertise as a core modeling input, not a footnote